Interactive and Explainable Region-guided Radiology Report Generation
Tim Tanida, Philip Müller, Georgios Kaissis, Daniel Rueckert
Abstract
The automatic generation of radiology reports has the potential to assist radiologists in the time-consuming task of report writing. Existing methods generate the full report from image-level features, failing to explicitly focus on anatomical regions in the image. We propose a simple yet effective region-guided report generation model that detects anatomical regions and then describes individual, salient regions to form the final report. While previous methods generate reports without the possibility of human intervention and with limited explainability, our method opens up novel clinical use cases through additional interactive capabilities and introduces a high degree of transparency and explainability. Comprehensive experiments demonstrate our method's effectiveness in report generation, outperforming previous state-of-the-art models, and highlight its interactive capabilities. The code and checkpoints are available at https://github.com/ ttanida/rgrg . * Equal contribution Region-guided Report Generation Model Generated Report The right lung is clear. Mild to moderate left pleural effusion as well as adjacent left basal atelectasis. Mild to moderate cardiomegaly. There is thoracolumbar dextroscoliosis. Left mid lung zone: Generated: Moderate left pleural effusion and moderate left lower lobe atelectasis are unchanged. Reference: Atelectasis of the left lower lobe with potential accompanying small left pleural effusion. Abdomen: Generated: NG tube tip is in the stomach. Reference: Nasogastric tube is in unchanged position. Cardiac silhouette: Generated: Moderate cardiomegaly persists. Reference: Unchanged moderate cardiomegaly. ground-truth prediction Right mid lung zone: Generated: Right lower lobe pneumonia. Reference: There is persistent subtle airspace opacity in the right mid to lower lung, this may reflect the residua of the patient's known pneumonia. Left lung: Generated: There is no pleural effusion or pneumothorax. No acute cardiopulmonary process. Reference: The left lung is clear. No pleural effusion seen.
Ask about this paper
Your agent reads all of it.
Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.
Your agent calls
Luneget_paper_fulltext
Free to start. No credit card required.
Terminal
Install the CLIlune papers fulltext e4373ad3-dd00-4359-93d7-83f0fffbb7a9Cited by top-tier papers34
- PromptMRG: Diagnosis-Driven Prompts for Medical Report GenerationHaibo Jin, Haoxuan Che, Yi Lin, Hao ChenAAAI 2024 · 168 citations
- The Impact of Imperfect XAI on Human-AI Decision-MakingKatelyn Morrison, Philipp Spitzer, Violet Turri, Michelle Feng et al.CSCW 2024 · 60 citations
- Better Tokens for Better 3D: Advancing Vision-Language Modeling in 3D Medical ImagingIbrahim Ethem Hamamci, Sezgin Er, Suprosanna Shit, Hadrien Reynaud et al.NeurIPS 2025 · 23 citations
- Radiology Report Generation via Multi-objective Preference OptimizationTing Xiao, Lei Shi, Peng Liu, Zhe Wang et al.AAAI 2025 · 21 citations
- UniMedVL: Unifying Medical Multimodal Understanding and Generation through Observation-Knowledge-AnalysisJunzhi Ning, Wei Li, Cheng Tang, Jiashi Lin et al.ICML 2026 · 13 citations
Builds on7
- BERTScore: Evaluating Text Generation with BERTTianyi Zhang, Varsha Kishore, Felix Wu, Kilian Q. Weinberger et al.ICLR 2020 · 8,443 citations
- Generating Radiology Reports via Memory-driven TransformerZhihong Chen, Yan Song, Tsung-Hui Chang, Xiang WanEMNLP 2020 · 552 citations
- When Radiology Report Generation Meets Knowledge GraphYixiao Zhang, Xiaosong Wang, Ziyue Xu, Qihang Yu et al.AAAI 2020 · 391 citations
- Cross-modal Memory Networks for Radiology Report GenerationZhihong Chen, Yaling Shen, Yan Song, Xiang WanACL 2021
- Say As You Wish: Fine-Grained Control of Image Caption Generation With Abstract Scene GraphsShizhe Chen, Qin Jin, Peng Wang, Qi WuCVPR 2020
Related papers
- AOR: Anatomical Ontology-Guided Reasoning for Medical Large Multimodal Model in Chest X-Ray InterpretationQingqiu Li, Zihang Cui, Seongsu Bae, Jilan Xu et al.NeurIPS 2025 · 10 citations
- PriorRG: Prior-Guided Contrastive Pre-training and Coarse-to-Fine Decoding for Chest X-ray Report GenerationKang Liu, Zhuoqi Ma, Zikang Fang, Yunan Li et al.AAAI 2026 · 5 citations
- Enhanced Contrastive Learning with Multi-view Longitudinal Data for Chest X-ray Report GenerationKang Liu, Zhuoqi Ma, Xiaolu Kang, Yunan Li et al.CVPR 2025
- ORGAN: Observation-Guided Radiology Report Generation via Tree ReasoningWenjun Hou, Kaishuai Xu, Yi Cheng, Wenjie Li et al.ACL 2023 · 36 citations
- Fine-Grained Image-Text Alignment in Medical Imaging Enables Explainable Cyclic Image-Report GenerationWenting Chen, Linlin Shen, Jingyang Lin, Jiebo Luo et al.ACL 2024 · 16 citations
